Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms

deepmind.google

Post reply on HN
Print view View original

11–20 of 298 posts

Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms

#11

Post by IncreasePosts »

ldjkfkdsjnv wrote: post #3

Software engineering will be completely solved. Even systems like v0 are astounding in their ability to generate code, and are very primitive to whats coming. I get downvoted on HN for this opinion, but its truly going to happen. Any system that can produce code, test the code, and iterate if needed will eventually outperform humans. Add in the reinforcement learning, where they can run the code, and train the model…

> Any system that can produce code, test the code, and iterate if needed

That isn't every problem in software engineering.

Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms

#12

Post by sannysanoff »

nevertoolate wrote: post #6
ldjkfkdsjnv wrote: post #3

Software engineering will be completely solved. Even systems like v0 are astounding in their ability to generate code, and are very primitive to whats coming. I get downvoted on HN for this opinion, but its truly going to happen. Any system that can produce code, test the code, and iterate if needed will eventually outperform humans. Add in the reinforcement learning, where they can run the code, and train the model…

It is not that you get downvoted because they don’t understand you, it is because you sell your opinion as fact, like an apostle. For example what does it mean that software engineering is solved?

Prophets are always beaten by average citizens, because prophecy is always unpleasant. It can't be otherwise. At the same time, you can't tell right away whether a person is really a prophet, because it becomes known much later. That's probably why beating them (the simplest solution) turns out to be the most observed.

Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms

#13

Post by markisus »

The paper does not give that many details about the evolution part. Normally, evolutionary algorithms contain some cross-over component where solutions can breed with each other. Otherwise it's better classified as hill climbing / beam search.

Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms

#14

Post by TechDebtDevin »

xianshou wrote: post #7

Calling it now - RL finally "just works" for any domain where answers are easily verifiable. Verifiability was always a prerequisite, but the difference from prior generations (not just AlphaGo, but any nontrivial RL process prior to roughly mid-2024) is that the reasoning traces and/or intermediate steps can be open-ended with potentially infinite branching, no clear notion of "steps" or nodes and edges in the game…

Most things are verifiable, just not with code. I'm not particularly excited for a world where everything is predictable. This is coming from a guy who loves forecasting/prediction modeling too, but one thing I hate about prediction modeling, especially from a hobbyist standpoint is data. Its very hard to get useful data. Investors will literally buy into hospital groups to get medical data for example.

There are monopolies on the coolest sets of data in almost all industries, all the RL in the world won't do us any good if those companies doing the data hoarding are only using it to forecast outcomes that will make them more money, not what can be done to better society.

Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms

#15

Post by handfuloflight »

sannysanoff wrote: post #12
nevertoolate wrote: post #6

Earlier quoted context omitted.

It is not that you get downvoted because they don’t understand you, it is because you sell your opinion as fact, like an apostle. For example what does it mean that software engineering is solved?

Prophets are always beaten by average citizens, because prophecy is always unpleasant. It can't be otherwise. At the same time, you can't tell right away whether a person is really a prophet, because it becomes known much later. That's probably why beating them (the simplest solution) turns out to be the most observed.

> because prophecy is always unpleasant.

Not necessarily. 'Gospel' is translated as good news. The unpleasant news tends towards those within the power structure that the prophet challenges.

Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms

#16

Post by jasonjmcghee »

> AlphaEvolve achieved up to a 32.5% speedup for the FlashAttention kernel implementation in Transformer-based AI models

> In roughly 75% of cases, it rediscovered state-of-the-art solutions, to the best of our knowledge.

> And in 20% of cases, AlphaEvolve improved the previously best known solutions

These sound like incredible results. I'd be curious what kind of improvements were made / what the improvements were.

Like, was that "up to a 32.5% speedup" on some weird edge case and it was negligible speed up otherwise? Would love to see the benchmarks.

Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms

#17

Post by smattiso »

xianshou wrote: post #7

Calling it now - RL finally "just works" for any domain where answers are easily verifiable. Verifiability was always a prerequisite, but the difference from prior generations (not just AlphaGo, but any nontrivial RL process prior to roughly mid-2024) is that the reasoning traces and/or intermediate steps can be open-ended with potentially infinite branching, no clear notion of "steps" or nodes and edges in the game…

Are there platforms that make such training more streamlined? Say I have some definition of success for a given problem and it’s data how do I go about generating said RL model as fast and easily as possible?

Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms

#18

Post by vrm »

smattiso wrote: post #17
xianshou wrote: post #7

Calling it now - RL finally "just works" for any domain where answers are easily verifiable. Verifiability was always a prerequisite, but the difference from prior generations (not just AlphaGo, but any nontrivial RL process prior to roughly mid-2024) is that the reasoning traces and/or intermediate steps can be open-ended with potentially infinite branching, no clear notion of "steps" or nodes and edges in the game…

Are there platforms that make such training more streamlined? Say I have some definition of success for a given problem and it’s data how do I go about generating said RL model as fast and easily as possible?

We're working on an OSS industrial-grade version of this at TensorZero but there's a long way to go. I think the easiest out of the box solution today is probably OpenAI RFT but that's a partial solve with substantial vendor lock-in.

Re: AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms

#20

Post by schmidtleonard »

jasonjmcghee wrote: post #16

> AlphaEvolve achieved up to a 32.5% speedup for the FlashAttention kernel implementation in Transformer-based AI models > In roughly 75% of cases, it rediscovered state-of-the-art solutions, to the best of our knowledge. > And in 20% of cases, AlphaEvolve improved the previously best known solutions These sound like incredible results. I'd be curious what kind of improvements were made / what the improvements were.…

Remember that GPUs have cache hierarchies and matching block sizes to optimally hit those caches is a big win that you often don't get by default, just because the number of important kernels times important GPUs times effort to properly tune one is greater than what people are willing to do for others for free in open source. Not to mention kernel fusion and API boundaries that socially force suboptimal choices for the sake of clarity and simplicity.

It's a very impressive result, but not magic, but also not cheating!

Post reply on HN